Jieyuan Pei

裴杰远

B.Eng. Intelligent Science & Technology
Zhejiang University of Technology · expected June 2027
Research intern · AIR, Tsinghua University
AI research intern · Hithink RoyalFlush

I want to build physical intelligence you can trust outside the lab — models that still hold up when the real world shifts scale, degrades, or hands them something they have never seen. I chase that in both directions at once: letting science compute what it could not compute before, and letting embodied agents act reliably in the world instead of only on a benchmark.

Applying for 2027 Fall MPhil / PhD.

Researchthree threads, one method

Embodied VLA

Robot memory, long-horizon tasks, test-time training, world models, and decision generalization for vision–language–action policies.

AI for Physics

Neural operators, PDE surrogates, engineering simulation, and scientific ML that transfers across geometries and resolutions.

AI for Remote Sensing

Spatial–spectral fusion, cross-scale and degradation modelling, operator-based imaging under realistic transfer.

Papersbold = me · * equal contribution · click a panel for the full figure

HNO teaser: near/far-field decomposition, hierarchical tree, and its embedding on a Lorentz hyperboloid

ICML 2026

Hyperbolic Neural Operator

Jieyuan Pei, Zhuoxuan Li, Wei Li, Haobo Zhang, Jiawei Jiang, Jianwei Zheng

Lorentz-distance attention for multiscale near–far interactions in PDE surrogates, evaluated on six standard benchmarks and two unstructured-mesh CFD tasks.

Paper PDF → Abstract & text → Project page → Code →

S3O architecture: multi-scale embedding, S3O backbone, and the hard location selection block

CVPR 2026

S³O: Selective Spatial–Spectral Operator for Cross-Scale Fusion

Jieyuan Pei^*, Wei Li^*, Zhuoxuan Li, Junwei Zhu, Meiyi Lu, Jiawei Jiang, Chenyu Wang, Jianwei Zheng

0.3–1.4 dB gains on three datasets at up to 4× lower compute than heavy Transformer / Mamba baselines.

Paper → Code →

Latent spectral operator pipeline: patchify, coordinate-to-latent projection, solve on a trigonometric basis, project back

ICML 2026

Solving Spatial–Spectral Fusion with Latent Spectral Operators

Wei Li, Jieyuan Pei, Junnan Xu, Xuanfeng Ding, Junwei Zhu, Wanjun Chen, Jianwei Zheng

+0.160 PSNR on CAVE ×4/×8 with 4.4% / 6.9% SAM reduction.

Paper → Project page → Code →

StarFus-Net U-Net with asymmetric spatial measurement and spectral prior paths

ICASSP 2026

Asymmetric StarFus: Learning Incoherent Measurements for Semantics-Aware Spatial–Spectral Fusion

Jieyuan Pei, Wei Li, Zhuoxuan Li, Junwei Zhu, Chuangjie Fang, Jianwei Zheng

Paper → Code →

Five-stage fusion pipeline with parallel spatial and frequency branches and a semantic transformer

IEEE TGRS

S²TA-Fuse: Semantic-Superpixel Tokenized Attention for Spatial–Spectral Fusion

Jiawei Jiang^*, Wei Li^*, Jieyuan Pei, Junwei Zhu, Honghui Xu, Yuchao Feng, Jianwei Zheng

Paper →

Mag-Mamba framework: magnetic phase encoder feeding a Mamba layer with rotation control

KDD 2026 · Oral

Mag-Mamba: Modeling Coupled Spatiotemporal Asymmetry for POI Recommendation

Zhuoxuan Li^*, Tangwei Ye^*, Jieyuan Pei, Haina Liang, Zhongyuan Lai, Zihan Liu, Yiming Wu, Qi Zhang, Liang Hu

arXiv →

RoboMemArena overview: annotation pipeline, dataset statistics, baseline comparison, and real-world evaluation

arXiv:2605.10921

RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark

Huashuo Lei^*, Wenxuan Song^*, Huarui Zhang, Jieyuan Pei, Jiayi Chen, Haodong Yan, Han Zhao, Pengxiang Ding, Zhipeng Zhang, Lida Huang, Donglin Wang, Yan Wang, Haoang Li

26 tasks, 2,600 demonstrations, 2.8M frames; mean trajectory 1,076 steps.

arXiv → Project page → Code →